tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-30 20:58:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : add pre-tokenizer regexes for BLOOM and gpt3-finnish (#8850)

Browse Source
This commit is contained in:
Esko Toivonen
2024-08-15 10:17:12 +03:00
committed by GitHub
parent d5492f0525
commit 6bda7ce6c3
5 changed files with 19 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-vocab.cpp
View File

@ -410,6 +410,8 @@ struct llm_tokenizer_bpe {
};
break;
case LLAMA_VOCAB_PRE_TYPE_PORO:
case LLAMA_VOCAB_PRE_TYPE_BLOOM:
case LLAMA_VOCAB_PRE_TYPE_GPT3_FINNISH:
regex_exprs = {
" ?[^(\\s|.,!?…。，、।۔،)]+",
};